Instruct-GPT + Mind's Eye
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Google,Dartmouth College
- Organisation type
- Industry,Academia
- Country
- United States of America
- Published
- 11 October 2022
- Authors
- Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, Andrew M. Dai
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Quantitative reasoning
- Base model
- InstructGPT 175B
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 176.5B
- Training data
- tokens
Two models: a LM that converts the input to code for a physics simulator, and a foundation model (InstructGPT) "the resulting models have 0.3B and 1.5B parameters (used as default)" InstructGPT is 175B. 175B+1.5B = 176.5B
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- Google TPU v3
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 101
Sources
Where this record came from and when it was last checked.
- Reference
- Mind's Eye: Grounded Language Model Reasoning through Simulation
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
Instruct-GPT + Mind's Eye was published by Google,Dartmouth College, in United States of America, in October 2022. The organisation is categorised as industry,Academia.
It works in Language, and is recorded as doing quantitative reasoning.
It is derived from InstructGPT 175B rather than trained from scratch, which is the usual way a specialised model is produced.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
Instruct-GPT + Mind's Eye — common questions
Who created Instruct-GPT + Mind's Eye?
Instruct-GPT + Mind's Eye was published by Google,Dartmouth College, based in United States of America, categorised as industry,Academia.
When was Instruct-GPT + Mind's Eye released?
Instruct-GPT + Mind's Eye was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Instruct-GPT + Mind's Eye used for?
Instruct-GPT + Mind's Eye works in Language, and is recorded as handling quantitative reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Instruct-GPT + Mind's Eye?
None. Instruct-GPT + Mind's Eye is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is Instruct-GPT + Mind's Eye open source?
No. Instruct-GPT + Mind's Eye has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Instruct-GPT + Mind's Eye have?
Instruct-GPT + Mind's Eye has 176.5B parameters. Two models: a LM that converts the input to code for a physics simulator, and a foundation model (InstructGPT) "the resulting models have 0.3B and 1.5B parameters (used as default)" InstructGPT is 175B. 175B+1.5B = 176.5B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.